Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
ONNX files exported from Kokoro 1.0. Voices have been converted to HDF5 and the speed input now uses type float32 (originally int64).
Model source
Source description
ONNX files exported from Kokoro 1.0. Voices have been converted to HDF5 and the speed input now uses type float32 (originally int64).
Sources
1 sourceVerified Sep 21
Model artifacts
55 artifactsSource excerpts
2 excerpts--- base_model: - hexgrad/Kokoro-82M pipeline_tag: text-to-speech tags: - onnx --- # Kokoro 1.0 [ONNX] ONNX files exported from [Kokoro 1.0](https://huggingface.co/hexgrad/Kokoro-82M). Voices have been converted to HDF5 and the `speed` input now uses type `float32` (originally `int64`).
voices/af_aoede.h5
h5 · 516 KB · SHA-256 a4f20c98e19e…e5cf · Hugging Face
Source context: 5 downloads · 0 likes · Pipeline text-to-speech · Repo alexisStacksCode/Kokoro-1.0-ONNX
